SEARCH · Search NASA

Results for “Language model”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 379 records · Page 21

All sources NASA NTRS DOE OSTI

NASA NTRS1992

User's guide to the Reliability Estimation System Testbed (REST)

The Reliability Estimation System Testbed is an X-window based reliability modeling tool that was created to explore the use of the Reliability Modeling Language (RML). RML was defined to support several reliability analysis techniques including modularization, graphical representation, Failure Mode Effects Simulation (FMES), and parallel processing. These techniques are most useful in modeling large systems. Using modularization, an analyst can create reliability models for individual system components. The modules can be tested separately and then combined to compute the total system reliability. Because a one-to-one relationship can be established between system components and the reliability modules, a graphical user interface may be used to describe the system model. RML was designed to permit message passing between modules. This feature enables reliability modeling based on a run time simulation of the system wide effects of a component's failure modes. The use of failure modes effects simulation enhances the analyst's ability to correctly express system behavior when using the modularization approach to reliability modeling. To alleviate the computation bottleneck often found in large reliability models, REST was designed to take advantage of parallel processing on hypercube processors.

Nicol, David M.↗

DOE OSTI2026

Deep learning for time series forecasting: a survey of recent advances

Time series forecasting plays a critical role in numerous real-world applications, such as finance, healthcare, transportation, and scientific computing. In recent years, deep learning has become a powerful tool for modeling complex temporal patterns and improving forecasting accuracy. This survey provides an overview of recent deep learning approaches for time series forecasting, involving various architectures including RNNs, CNNs, GNNs, transformers, large language models, MLP-based models, and diffusion models. We first identify key challenges in the field, such as temporal dependency, efficiency, and cross-variable dependency, which drive the development of forecasting techniques. Then, the general advantages and limitations of each architecture are discussed to contextualize their adaptation in time series forecasting. Furthermore, we highlight promising design trends like multi-scale modeling, decomposition, and frequency-domain techniques, which are shaping the future of the field. This paper serves as a compact reference for researchers and practitioners seeking to understand the current landscape and future trajectory of deep learning in time series forecasting.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Agentic artificial intelligence for multistage physics experiments at a large-scale user facility particle accelerator

We present a language-model-driven agentic artificial intelligence (AI) system to autonomously execute multistage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by 2 orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.

Accelerator/storage ring control systems↗

NASA NTRS2013

Aquarius' Object-Oriented, Plug and Play Component-Based Flight Software

The Aquarius mission involves a combined radiometer and radar instrument in low-Earth orbit, providing monthly global maps of Sea Surface Salinity. Operating successfully in orbit since June, 2011, the spacecraft bus was furnished by the Argentine space agency, Comision Nacional de Actividades Espaciales (CONAE). The instrument, built jointly by NASA's Caltech/JPL and Goddard Space Flight Center, has been successfully producing expectation-exceeding data since it was powered on in August of 2011. In addition to the radiometer and scatterometer, the instrument contains an command & data-handling subsystem with a computer and flight software (FSW) that is responsible for managing the instrument, its operation, and its data. Aquarius' FSW is conceived and architected as a Component-based system, in which the running software consists of a set of Components, each playing a distinctive role in the subsystem, instantiated and connected together at runtime. Component architectures feature a well-defined set of interfaces between the Components, visible and analyzable at the architectural level (see [1]). As we will describe, this kind of an architecture offers significant advantages over more traditional FSW architectures, which often feature a monolithic runtime structure. Component-based software is enabled by Object-Oriented (OO) techniques and languages, the use of which again is not typical in space mission FSW. We will argue in this paper that the use of OO design methods and tools (especially the Unified Modeling Language), as well as the judicious usage of C++, are very well suited to FSW applications, and we will present Aquarius FSW, describing our methods, processes, and design, as a successful case in point.

Component Architecture↗

NASA NTRS2007

Mission Simulation Toolkit

The Mission Simulation Toolkit (MST) is a flexible software system for autonomy research. It was developed as part of the Mission Simulation Facility (MSF) project that was started in 2001 to facilitate the development of autonomous planetary robotic missions. Autonomy is a key enabling factor for robotic exploration. There has been a large gap between autonomy software (at the research level), and software that is ready for insertion into near-term space missions. The MST bridges this gap by providing a simulation framework and a suite of tools for supporting research and maturation of autonomy. MST uses a distributed framework based on the High Level Architecture (HLA) standard. A key feature of the MST framework is the ability to plug in new models to replace existing ones with the same services. This enables significant simulation flexibility, particularly the mixing and control of fidelity level. In addition, the MST provides automatic code generation from robot interfaces defined with the Unified Modeling Language (UML), methods for maintaining synchronization across distributed simulation systems, XML-based robot description, and an environment server. Finally, the MSF supports a number of third-party products including dynamic models and terrain databases. Although the communication objects and some of the simulation components that are provided with this toolkit are specifically designed for terrestrial surface rovers, the MST can be applied to any other domain, such as aerial, aquatic, or space.

Pisaich, Gregory↗

DOE OSTI2026

Site-decorated model for unconventional frustrated magnets: Ultranarrow phase crossover and two-dimensional spin reversal transition

Here, the site-decorated Ising model is introduced to advance the understanding and experimental realization of the recently discovered one-dimensional (1D) finite-temperature ultranarrow phase crossover in an external magnetic field, while mitigating the geometric complexities of traditional bond-decorated models. The unconventional frustration and physics are clarified by exactly mapping the 1D site-decorated Ising model in a magnetic field onto a zero-field bond-decorated 𝐽 1 −𝐽 2 Ising model with conventional geometrical frustration. Furthermore, although higher-dimensional Ising models in an external field remain unsolved exactly, an exact solution for a spin-reversal transition—driven by an exotic, hidden half-ice, half-fire state induced by site decoration—is derived. This transition, triggered by a slight variation in temperature or magnetic field—without changing its direction—even in the weak-field limit, offers a promising route toward energy-efficient applications such as data storage and processing. The results suggest that site decoration offers an avenue for materials and device design, particularly in systems such as mixed 𝑑−𝑓 compounds, optical lattices, and neural networks, calling for further studies with site-decorated Heisenberg models. In addition, the site-decorated model offers a rigorous test ground for artificial intelligence (AI) in science, as the analytic derivation of the present results was not only validated but also improved by a general-purpose large language model, inspiring the use of AI as scientific discoverer.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

NASA NTRS2011

An Overview of NASA's Integrated Design and Engineering Analysis (IDEA) Environment

Historically, the design of subsonic and supersonic aircraft has been divided into separate technical disciplines (such as propulsion, aerodynamics and structures), each of which performs design and analysis in relative isolation from others. This is possible, in most cases, either because the amount of interdisciplinary coupling is minimal, or because the interactions can be treated as linear. The design of hypersonic airbreathing vehicles, like NASA's X-43, is quite the opposite. Such systems are dominated by strong non-linear interactions between disciplines. The design of these systems demands that a multi-disciplinary approach be taken. Furthermore, increased analytical fidelity at the conceptual design phase is highly desirable, as many of the non-linearities are not captured by lower fidelity tools. Only when these systems are designed from a true multi-disciplinary perspective, can the real performance benefits be achieved and complete vehicle systems be fielded. Toward this end, the Vehicle Analysis Branch at NASA Langley Research Center has been developing the Integrated Design and Engineering Analysis (IDEA) Environment. IDEA is a collaborative environment for parametrically modeling conceptual and preliminary designs for launch vehicle and high speed atmospheric flight configurations using the Adaptive Modeling Language (AML) as the underlying framework. The environment integrates geometry, packaging, propulsion, trajectory, aerodynamics, aerothermodynamics, engine and airframe subsystem design, thermal and structural analysis, and vehicle closure into a generative, parametric, unified computational model where data is shared seamlessly between the different disciplines. Plans are also in place to incorporate life cycle analysis tools into the environment which will estimate vehicle operability, reliability and cost. IDEA is currently being funded by NASA?s Hypersonics Project, a part of the Fundamental Aeronautics Program within the Aeronautics Research Mission Directorate. The environment is currently focused around a two-stage-to-orbit configuration with a turbine-based combined cycle (TBCC) first stage and a reusable rocket second stage. IDEA will be rolled out in generations, with each successive generation providing a significant increase in capability, either through increased analytic fidelity, expansion of vehicle classes considered, or by the inclusion of advanced modeling techniques. This paper provides the motivation behind the current effort, an overview of the development of the IDEA environment (including the contents and capabilities to be included in Generation 1 and Generation 2), and a description of the current status and detail of future plans.

Robinson, Jeffrey S.↗

DOE OSTI2026

SetGo: Metadata Readiness for Scientific AI Datasets

Scientific datasets intended for AI use require both computational readiness for model training and metadata readiness for discovery, sharing, and reuse. The Readiness Engine for Data Integration (REDI) addresses computational readiness, but no corresponding tool evaluates whether a dataset’s metadata are sufficiently complete, governed, and standards-compliant for publication and agent-based consumption. Existing FAIR assessors operate only on published repository records, and no single system covers FAIR compliance, licensing, provenance, governance, reproducibility, and catalog readiness together. We present SetGo, an open-source Python toolkit that assesses and repairs metadata readiness across these six dimensions before a dataset is published or archived. Applied to four scientific corpora, SetGo surfaces deficiencies that general-purpose tools do not detect: ERA5 climate metadata scores 4% on ACDD 1.3 compliance; materials datasets fail OPTIMADE species-definition requirements; and PDB-derived proteomics data carries licensing terms incompatible with standard SPDX identifiers. Guided enrichment raises overall FAIR scores from 52–57% to 81–91%, and a single setgo publish command pushes to Hugging Face Hub, CKAN, or OpenMetadata with ML Commons Croissant 1.0 metadata sidecars. To support interactive and automated workflows, SetGo integrates with coding agents powered by large language models (LLMs) through a /setgo skill that enables natural-language execution of the full assess–enrich–publish loop, with user involvement limited to supplying missing metadata values.

Wilkinson, Sean [ORNL] (ORCID:0000000214437479)↗

DOE OSTI2025

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1992

Advanced techniques in reliability model representation and solution

The current tendency of flight control system designs is towards increased integration of applications and increased distribution of computational elements. The reliability analysis of such systems is difficult because subsystem interactions are increasingly interdependent. Researchers at NASA Langley Research Center have been working for several years to extend the capability of Markov modeling techniques to address these problems. This effort has been focused in the areas of increased model abstraction and increased computational capability. The reliability model generator (RMG) is a software tool that uses as input a graphical object-oriented block diagram of the system. RMG uses a failure-effects algorithm to produce the reliability model from the graphical description. The ASSURE software tool is a parallel processing program that uses the semi-Markov unreliability range evaluator (SURE) solution technique and the abstract semi-Markov specification interface to the SURE tool (ASSIST) modeling language. A failure modes-effects simulation is used by ASSURE. These tools were used to analyze a significant portion of a complex flight control system. The successful combination of the power of graphical representation, automated model generation, and parallel computation leads to the conclusion that distributed fault-tolerant system architectures can now be analyzed.

Palumbo, Daniel L.↗

NASA NTRS2019

Enabling Assurance in the MBSE Environment

Evans, John W.↗

DOE OSTI2025

Extracting Material Property Measurements from Scientific Literature with Limited Annotations

Extracting material property data from scientific text is pivotal for advancing data-driven research in chemistry and materials science; however, the extensive annotation effort required to produce training data for named entity recognition (NER) models for this task often makes it a barrier to extracting specialized data sets. Here, in this work, we present a comparative study of the conventional, supervised NER methodology to alternative few-shot learning architectures and large language model (LLM)-based approaches that mitigate the need to label large training data sets. We find that the best-performing LLM (GPT-4o) not only excels in directly extracting relevant material properties based on limited examples but also enhances supervised learning through data augmentation. We supplement our findings with error and data quality assessments to provide a nuanced understanding of factors that impact property measurement extraction.

36 MATERIALS SCIENCE↗

NASA NTRS2020

Enabling Assurance in the MBSE Environment

A number of specific benefits that fit within the hallmarks of effective development are realized with implementation of model-based approaches to systems and assurance. Model Based Systems Engineering (MBSE) enabled by standardized modeling languages (e.g., SysML®) is at the core. These benefits in the context of spaceflight system challenges can include [1]: • Improved management of complex development • Reduced risk in the development process • Improved cost management • Improved design decisions With appropriate modeling techniques the assurance community also can improve early oversight and insight into project development. NASA has shown the basic constructs of SysML in an MBSE environment offer several key advantages, within a Model Based Mission Assurance (MBMA) initiative [2, 3]. These include the following: • Model viewpoints that promote rapid and systematic assessment of requirements coverage, hazard tagging and risk management • Embedded safety assessments for launch vehicles • Deployment of model assisted development of reliability products - Failure Modes and Effects Analyses (FMEAs) and Fault Trees • Test Planning • Validation and Verification of complex functions • Support of Assurance Case development for complex systems In addition, while there are benefits to be harvested, there is a realization that these do not come without effort and cost. Enabling model-based approaches requires structure, not only in an organizational context, but in a modeling context as well. There can be a steep learning curve and costs associated to train skilled modelers. But, on the other hand, not all of the assurance community need to be modelers. Models themselves must conform to ontologies that enable assurance. This places constraints upon the models and modelers. Optimums have yet to be developed where resources and constraints on modeling must be traded off in the organization and modeling efforts for projects. A number of barriers need to be overcome, as well, which pose challenges to the developers of the software that supports MBSE/MBMA. Information and data must be made to flow seamlessly through the life cycle. Because there is a wide variety of tools used in the community, to avoid the problems of the past of silos, delays, and diverging interests, information should flow among these tools to support the “single source of truth” paradigm of MBSE. This will greatly facilitate MBMA and advancement of assurance functions.

Evans, John W.↗

DOE OSTI2026

matsim-agents v1.0

matsim-agents is a multi-agent AI framework for atomistic materials simulation and discovery. It orchestrates large language models (LLMs), machine-learned interatomic potentials (MLIPs), and DFT codes into a single agentic loop running on laptops and DOE leadership-class supercomputers. MULTI-AGENT ORCHESTRATION A LangGraph state machine with three nodes: a Planner that converts a natural-language research objective into structured tasks; an Executor that dispatches atomistic tools and loops until the queue is empty; and an Analyst that summarizes results into a human-readable report. State is checkpointed after every step and human-in-the-loop gates can be inserted at any edge. HYPOTHESIS-DRIVEN DISCOVERY CHAT An interactive REPL (matsim-agents chat) that couples LLM dialogue with atomistic simulation. Chemical formulas are automatically detected in conversation turns and trigger a full crystal-phase exploration: structure generation → relaxation → stability scoring → result injection back into the conversation, creating a closed hypothesis-refinement loop. CRYSTAL PHASE ENUMERATION Given a composition, the phase explorer enumerates prototypes by stoichiometry: elemental (fcc/bcc/hcp/sc/diamond), binary 1:1 (rocksalt/CsCl/zincblende/ wurtzite/fluorite/rutile), ternary 1:1:3 (cubic perovskite), ternary 1:2:4 (perovskite + spinel), quaternary 1:1:2:6 (Fm-3m double perovskite). 2-D prototypes (graphene, h-BN, MoS2 2H/1T) and multilayer stacking are also supported via --include-2d and --num-layers. SUPERCELL GENERATION AND SITE DECORATION Auto-tiling to a minimum atom count (--min-atoms), explicit NxNxN tiling (--supercell), symmetry-distinct site decorations (--n-orderings), and isotropic lattice-scale sweeps (--lattice-scales) for volume bracketing. MLFF RELAXATION AND STABILITY SCORING HydraGNN (multi-headed GNN) drives structure relaxation via ASE with FIRE, BFGS, or BFGSLineSearch. Stability output: delta-E/atom ranking across phases and a max-residual-force dynamical-stability proxy. Other MLIPs (MACE, NequIP, Orb) can be plugged in through the same interface. DFT BACKENDS Quantum ESPRESSO pw.x and VASP 6.6 are first-class labellers. Both have validated GPU builds and SLURM/PBS launchers for three DOE platforms: Frontier (AMD MI250X, ROCm), Aurora (Intel PVC, oneAPI), Perlmutter (NVIDIA A100, CUDA). QE produces ~100 binaries (pw.x, ph.x, epw.x, ...). VASP supports scf, relax, vc-relax, and vc-relax-shape run types. ACTIVE-LEARNING LOOP matsim-agents al run CONFIG.yaml drives an iterative HydraGNN-DFT loop: MD generates candidates → ensemble/MC-dropout uncertainty selects the most informative → DFT labels them in parallel inside one allocation → dataset grows → HydraGNN retrains → repeat. DFT backend is a single YAML toggle (dft.backend: vasp | qe). LLM-generated seed structures are supported (no curated POSCAR library needed). Config uses ${VAR}, ${VAR:-default}, ${VAR:?msg} shell-style substitution for cross-user/cross-site portability. LLM BACKENDS Ollama (local, default), vLLM (HPC multi-GPU serving), OpenAI, Anthropic, HuggingFace Transformers+Accelerate. Selected at runtime via flag or env var with no code changes. HPC PORTABILITY Same Python entry points run on Frontier (ROCm 7.2), Aurora (oneAPI), and Perlmutter (CUDA 12). DFT and ML stacks are never co-loaded in the same shell; they couple through the scheduler and filesystem. Advanced multi-node launchers (serve, discovery-chat, single-relaxation, active-learning, QE warm-start) are provided for all three platforms. CODABENCH COMPETITION BUNDLE A self-contained benchmark: 159 atomistic test structures across 11 material classes, 5 tasks (formation energy, forces, ML relaxation, AI-DFT relaxation, phase stability ranking), public/private leaderboard split (30/70), and four ready-to-run baselines: MACE-MP-0, HydraGNN, UMA, AllScAIP.

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗

DOE OSTI2024

GOLEM: GOld standard for Learning and Evaluation of Motifs

Motifs are distinctive, recurring, widely used idiom-like words or phrases, often originating from folklore, whose meaning is anchored in a narrative and have a significance as communicative devices across a wide range of media, including news, literature, and propaganda. Many motifs concisely imply a large constellation of culturally relevant information, and their broad usage suggests their cognitive importance as touchstones of cultural knowledge. As such, their detection is a step towards culturally aware natural language processing. We present GOLEM (GOld standard for Learning and Evaluation of Motifs) a dataset of English news articles, opinion pieces, and broadcast transcripts annotated for motific information. The dataset identifies 25,737 motif candidates across 34 motif types drawn from three cultural or national groups: Jewish, Irish, and Puerto Rican. The dataset contains 2,024,141 words split into 25,737 text snippets drawn from 8,073 articles. Each motif candidate is labeled according to a scheme which identifies the type of usage (motific, referential, eponymic, or unrelated), resulting in 1,743 actual motific instances in the data. Annotation was performed by individuals identifying as members of each group and achieved a Fleiss’ kappa (?) of > 0.55. In addition to the data, we demonstrate that classification of the candidate type is a challenging task for Large Language Models (LLMs) using a few-shot approach; recent models such as T5, FLAN-T5, GPT-2, and Llama 2 (7B) achieved a performance of 41% accuracy at best, where the majority class accuracy is 41% and the average chance accuracy is 27%. These data will support development of new models and approaches for detecting (and reasoning about) motific information in text.

motif, culture, natural language, artificial intel↗

NASA NTRS2012

Model-Based Systems Engineering Pilot Program at NASA Langley

NASA Langley Research Center conducted a pilot program to evaluate the benefits of using a Model-Based Systems Engineering (MBSE) approach during the early phase of the Materials International Space Station Experiment-X (MISSE-X) project. The goal of the pilot was to leverage MBSE tools and methods, including the Systems Modeling Language (SysML), to understand the net gain of utilizing this approach on a moderate size flight project. The System Requirements Review (SRR) success criteria were used to guide the work products desired from the pilot. This paper discusses the pilot project implementation, provides SysML model examples, identifies lessons learned, and describes plans for further use on MBSE on MISSE-X.

Vipavetz, Kevin G.↗

NASA NTRS2010

BGen: A UML Behavior Network Generator Tool

BGen software was designed for autogeneration of code based on a graphical representation of a behavior network used for controlling automatic vehicles. A common format used for describing a behavior network, such as that used in the JPL-developed behavior-based control system, CARACaS ["Control Architecture for Robotic Agent Command and Sensing" (NPO-43635), NASA Tech Briefs, Vol. 32, No. 10 (October 2008), page 40] includes a graph with sensory inputs flowing through the behaviors in order to generate the signals for the actuators that drive and steer the vehicle. A computer program to translate Unified Modeling Language (UML) Freeform Implementation Diagrams into a legacy C implementation of Behavior Network has been developed in order to simplify the development of C-code for behavior-based control systems. UML is a popular standard developed by the Object Management Group (OMG) to model software architectures graphically. The C implementation of a Behavior Network is functioning as a decision tree.

Huntsberger, Terry↗

NASA NTRS1990

A graphical language for reliability model generation

A graphical interface capability of the hybrid automated reliability predictor (HARP) is described. The graphics-oriented (GO) module provides the user with a graphical language for modeling system failure modes through the selection of various fault tree gates, including sequence dependency gates, or by a Markov chain. With this graphical input language, a fault tree becomes a convenient notation for describing a system. In accounting for any sequence dependencies, HARP converts the fault-tree notation to a complex stochastic process that is reduced to a Markov chain which it can then solve for system reliability. The graphics capability is available for use on an IBM-compatible PC, a Sun, and a VAX workstation. The GO module is written in the C programming language and uses the Graphical Kernel System (GKS) standard for graphics implementation. The PC, VAX, and Sun versions of the HARP GO module are currently in beta-testing.

Howell, Sandra V.↗